Reinforcement learning for the adaptive control of perception and action
Reinforcement learning for the adaptive control of perception and action
Adding temporary memory to ZCS
Adaptive Behavior
Switching and Finite Automata Theory: Computer Science Series
Switching and Finite Automata Theory: Computer Science Series
Evolution of Plastic Control Networks
Autonomous Robots
Genetic Algorithms for Multiobjective Optimization: FormulationDiscussion and Generalization
Proceedings of the 5th International Conference on Genetic Algorithms
Mobile Robot Miniaturisation: A Tool for Investigation in Control Algorithms
The 3rd International Symposium on Experimental Robotics III
An Artificial Life Approach for the Synthesis of Autonomous Agents
AE '95 Selected Papers from the European conference on Artificial Evolution
An evolutionary approach to quantify internal states needed for the woods problem
ICSAB Proceedings of the seventh international conference on simulation of adaptive behavior on From animals to animats
Intelligence Without Reason
Reinforcement learning with selective perception and hidden state
Reinforcement learning with selective perception and hidden state
Memory analysis and significance test for agent behaviours
Proceedings of the 8th annual conference on Genetic and evolutionary computation
| Hi-index | 0.00 |
In autonomous agent systems, memory is an important element to handle agent behaviors appropriately. We present the analysis of memory requirements for robotic tasks including wall following and corridor following. The robotic tasks are simulated with sensor modeling and motor actions in noisy environments. In this paper, control structures are based on finite state machines for memory-based controllers, and we use the evolutionary multiobjective optimization approach with two objectives, behavior performance and memory size. For each task, a quantitative approach to estimate internal states with a different number of sensors is applied and the best controllers are evaluated in several test environments to examine their generalization characteristics and efficiency. Finite state machines with a hierarchy of memory are also compared with feedforward neural networks for the behavior performance.